[2510.12077] Compressibility Measures Complexity: Minimum Description Length Meets Singular Learning Theory

Skip to main content

arXiv is now an independent nonprofit!<br>Learn more<br>&times;

Search arXiv

Press Enter to search &middot; Advanced search

-->

Statistics > Machine Learning

arXiv:2510.12077 (stat)

[Submitted on 14 Oct 2025]

Title:Compressibility Measures Complexity: Minimum Description Length Meets Singular Learning Theory

Authors:Einar Urdshals, Edmund Lau, Jesse Hoogland, Stan van Wingerden, Daniel Murfet<br>View a PDF of the paper titled Compressibility Measures Complexity: Minimum Description Length Meets Singular Learning Theory, by Einar Urdshals and 4 other authors

View PDF<br>HTML (experimental)

Abstract:We study neural network compressibility by using singular learning theory to extend the minimum description length (MDL) principle to singular models like neural networks. Through extensive experiments on the Pythia suite with quantization, factorization, and other compression techniques, we find that complexity estimates based on the local learning coefficient (LLC) are closely, and in some cases, linearly correlated with compressibility. Our results provide a path toward rigorously evaluating the limits of model compression.

Comments:<br>33 pages, 21 figures

Subjects:

Machine Learning (stat.ML); Machine Learning (cs.LG)

Cite as:<br>arXiv:2510.12077 [stat.ML]

(or<br>arXiv:2510.12077v1 [stat.ML] for this version)

https://doi.org/10.48550/arXiv.2510.12077

Focus to learn more

arXiv-issued DOI via DataCite

Submission history<br>From: Jesse Hoogland [view email]<br>[v1]<br>Tue, 14 Oct 2025 02:38:02 UTC (2,395 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled Compressibility Measures Complexity: Minimum Description Length Meets Singular Learning Theory, by Einar Urdshals and 4 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

stat.ML

next >

new<br>recent<br>| 2025-10

Change to browse by:

cs<br>cs.LG<br>stat

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

export BibTeX citation<br>Loading...

BibTeX formatted citation

&times;

loading...

Data provided by:

Bookmark

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .

Which authors of this paper are endorsers? |<br>Disable MathJax (What is MathJax?)

Major funding support from